[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN112162565B - Uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation - Google Patents

Uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation Download PDF

Info

Publication number
CN112162565B
CN112162565B CN202010851167.4A CN202010851167A CN112162565B CN 112162565 B CN112162565 B CN 112162565B CN 202010851167 A CN202010851167 A CN 202010851167A CN 112162565 B CN112162565 B CN 112162565B
Authority
CN
China
Prior art keywords
tower
unmanned aerial
aerial vehicle
machine
inspection
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010851167.4A
Other languages
Chinese (zh)
Other versions
CN112162565A (en
Inventor
许保瑜
蔡澍雨
王胜伟
杨增源
许德斌
张辉
周自更
葛兴科
陈海东
黄俊波
胡昌斌
徐家勇
宋庆
柏宇
侯建勋
钱晓明
张尚萌
梁介众
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yunnan Power Grid Co Ltd
Original Assignee
Yunnan Power Grid Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Yunnan Power Grid Co Ltd filed Critical Yunnan Power Grid Co Ltd
Priority to CN202010851167.4A priority Critical patent/CN112162565B/en
Publication of CN112162565A publication Critical patent/CN112162565A/en
Application granted granted Critical
Publication of CN112162565B publication Critical patent/CN112162565B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/10Simultaneous control of position or course in three dimensions
    • G05D1/101Simultaneous control of position or course in three dimensions specially adapted for aircraft

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The invention relates to an uninterrupted self-main-rod tower inspection method based on multi-machine collaborative operation, which comprises the following steps: and (5) data input, generating tower route data by the master, and automatically and finely inspecting the master or the slave. According to the invention, two mobile platforms are used for replacing the flying spot and the landing spot, so that the return range of the unmanned aerial vehicle after completing the target inspection task is saved, the range of single operation of the unmanned aerial vehicle is further, and the single inspection target is more.

Description

Uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation
Technical Field
The invention relates to the field of unmanned aerial vehicle automatic control, in particular to an uninterrupted self-main-rod tower inspection method based on multi-machine collaborative operation.
Background
The existing unmanned aerial vehicle inspection mode adopts the way of planning a route in advance on the ground through route planning software to carry out inspection operation on an inspection route. The existing unmanned aerial vehicle inspection mode further comprises the step of adopting a manual operation unmanned aerial vehicle to conduct inspection.
The traditional inspection operation mode has the advantages that the effective operation distance is small due to the fact that actual signal shielding exists in the inspection operation and maintenance work in the mountainous area and the hilly area. And also because of artificial factors, the inspection photo data standard is not uniform, the data quality is uneven, the inspection efficiency is low, and the like.
Disclosure of Invention
In order to solve the technical problems, the invention provides an uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation, which comprises the following steps:
an uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation comprises the following steps:
step (1), data input
Inputting unmanned aerial vehicle and line pole tower information through an unmanned aerial vehicle on-site background management system;
step (2), generating pole tower route data by the master machine
Distributing account information of operators through a background, and downloading corresponding pole tower route data after the operators newly create an operation task; or taking off from a first field mobile platform of the first operation tower by using an unmanned aerial vehicle carrying an onboard computer, flying along a preset rough route, automatically finishing recording of a fine route by the onboard computer during flying, and accurately lowering a second field mobile platform of the second operation tower to generate accurate route data of the tower;
step (3), automatic fine inspection of the mother machine or the son machine
After the mother machine generates the accurate route, a first team of field operators arrive at a first field mobile platform, a vehicle-mounted unmanned aerial vehicle take-off and landing platform is used for controlling a common unmanned aerial vehicle, or the mother machine is directly used in a complex terrain environment, and automatic and refined inspection of the towers is performed based on the accurate route data; meanwhile, a second team of field operators arrive at a second field mobile platform and send return coordinate data; after the main machine or the sub machine starts to take off and work, the field personnel of the first field mobile platform are transferred to the position of a third working tower; after the second team of field operators fly off the unmanned aerial vehicle, the second team of field operators are transferred to a fourth operation tower position, and the first field mobile platform and the second field mobile platform are alternately used as take-off landing points; until the task is finished.
And (3) landing after the unmanned aerial vehicle finishes operation, carrying out power conversion and data uploading, and then taking off again to carry out the next flight operation and landing to a descent point.
Further, the method also comprises the step (5) of carrying out induction and arrangement on the inspection data by operators after finishing the operation task, and then uploading the inspection data, wherein the field operation task is finished.
Further, in the step (2), the formation process of the accurate route of the tower is as follows:
the edge computing equipment on the master machine collects information of video acquisition units of different waypoints, simply filters video streams, and then detects each frame of picture based on a neural network;
the airborne computer collects detection results of edge computing equipment, controls the unmanned aerial vehicle and the video acquisition unit according to the detection results, shoots detection objects of different waypoints, records GPS information, time, shooting times, adjustment times, stability and definition of the waypoints, and finally obtains a precise route capable of accurately shooting target detection objects in the same environment.
Further, after the unmanned aerial vehicle takes off, the unmanned aerial vehicle flies around the tower in a distance of 3-10 meters, and accurate positioning is carried out by using a GPS; the unmanned aerial vehicle sways within the range of 10-50 cm during hovering.
Further, the simple filtering of the video stream is specifically as follows:
after reaching an waypoint, the video acquisition unit performs large-scale scanning, the edge computing equipment starts a tower identification neural network, firstly identifies the position of the tower closest to the unmanned aerial vehicle, and identifies the type, the direction, the coordinates and the size of the tower from the video stream, wherein the identification speed is 10 frames per second; after the towers are identified, firstly, the towers in each frame are sheared out, so that sundries except the towers are filtered cleanly.
Further, the specific process of detecting each frame of picture based on the neural network is as follows:
amplifying and photographing each detected insulator in the graph, and switching the neural network to the object detection recognition neural network by the edge computing equipment; the neural network carries out detection object identification on the sheared tower pictures, and comprises an insulator, a tower brand, types, orientations, coordinates, sizes and definition of tower top angles and tower bottom supports; at this time, the onboard computer records the unmanned aerial vehicle coordinates, inclination angles, orientations, and camera sitting inclination angles, orientations as the first pose.
Further, the controller collects detection results of the edge computing equipment, and controls the unmanned aerial vehicle and the video collecting unit according to the detection results as follows:
step (1): based on the position of the first detector in the figure, the controller moves the camera so that the insulator is moved to the very center of the image, wherein image recognition tracks the insulator at a speed of 10 frames per second;
step (2): gradually amplifying and focusing to ensure that the size of the detection object is larger and larger in the middle, wherein the speed of 10 frames per second of image recognition tracks the insulator and calculates whether the insulator is clear or not, and the inclination angle of the camera is continuously controlled to keep the insulator at the center of the image all the time;
step (3): when the detected object is amplified to 1/4 of the total size of the picture, namely the width and the length are half of the picture, photographing the insulator;
step (4): and (3) restoring the focal length and the inclination angle of the camera to the first pose, and repeating the step (1) for the next detected object.
Further, after all the detected objects in the waypoints are scanned, the GPS information, time, photographing times, adjustment times, stability and definition of the waypoints are recorded, the unmanned aerial vehicle flies to the next waypoint, the insulators are photographed again at different angles, and the route recorded and produced after the inspection is completed, namely, a precise route capable of accurately photographing the target detection object in the same environment.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, two mobile platforms are used for replacing the flying spot and the landing spot, so that the return range of the unmanned aerial vehicle after completing the target inspection task is saved, the range of single operation of the unmanned aerial vehicle is further, and the single inspection target is more.
2. The uninterrupted inspection operation mode ensures that the vehicle does not need to wait for the unmanned aerial vehicle to return to the home but reaches the next inspection place in advance, thereby greatly improving the inspection operation efficiency.
3. According to the invention, an automatic fine inspection scheme of the unmanned aerial vehicle is adopted by utilizing a vehicle-mounted automatic flight platform, so that automatic fine operation can be realized in a complex environment, the liberation of productivity is facilitated, and the inspection efficiency is improved.
Drawings
Fig. 1 is a position relation diagram of inspection in the present embodiment;
fig. 2 is a flowchart of one of the inspection processes in the present embodiment.
Detailed Description
The following description of the embodiments will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. Based on the embodiments, all other embodiments that may be obtained by a person of ordinary skill in the art without making any inventive effort are within the scope of the present invention.
Unless otherwise defined, technical or scientific terms used in the embodiments of the present application should be given a general meaning as understood by one of ordinary skill in the art. The terms "first," "second," and the like, as used in this embodiment, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. "upper", "lower", "left", "right", "transverse", and "vertical", etc. are used only with respect to the orientation of the components in the drawings, these directional terms are relative terms, which are used for descriptive and clarity with respect thereto and which may vary accordingly with respect to the orientation in which the components are disposed in the drawings.
As shown in fig. 1, the uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation in this embodiment includes the following steps:
step (1), data input:
inputting unmanned aerial vehicle and line pole tower information through an unmanned aerial vehicle on-site background management system;
step (2), generating pole tower route data by the master machine
Distributing account information of operators through a background, and downloading corresponding pole tower route data after the operators newly create an operation task; or taking off from an A vehicle of the first operation tower by using an unmanned aerial vehicle (namely a mother machine) carrying an onboard computer, flying along a preset rough route, automatically finishing recording of a fine route by the onboard computer during the flying, accurately lowering a B vehicle of the second operation tower, and generating accurate route data of the tower;
step (3), automatic fine inspection of the mother machine or the son machine
After the master machine generates the accurate route, a first team of field operators arrive at the vehicle A, and the vehicle-mounted unmanned aerial vehicle take-off and landing platform is used for controlling a common unmanned aerial vehicle (namely a sub-machine), or the master machine is directly used in a complex terrain environment, and automatic and refined inspection of the pole tower is performed based on the accurate route data; meanwhile, a second team of on-site operators arrive at the B vehicle and send return coordinate data; after the main machine or the sub machine starts to take off and work, the on-site personnel of the vehicle A are transferred to the position of a third working tower; after the second team of field operators fly off the unmanned aerial vehicle, the second team of field operators are transferred to a fourth operation tower position, and the A vehicles and the B vehicles alternately serve as take-off landing points, as shown in fig. 1; until the task is finished.
And (4) landing after the unmanned aerial vehicle finishes operation, carrying out power conversion and data uploading, and then taking off again to carry out the next flight operation and landing to a descending point.
And (5) after finishing the operation task, the operator carries out induction and arrangement on the inspection data and then uploads the inspection data, and the field operation task is finished.
Aiming at the actual situation of a power transmission line, the unmanned aerial vehicle of the embodiment covers electromagnetic shielding materials and has the characteristic of strong electromagnetic environment interference resistance. In the aspect of equipment, can use current unmanned aerial vehicle automatic take-off and land platform, two sets of on-vehicle unmanned aerial vehicle operation management and control platforms, a set of portable miniature weather station and a set of aerial signal repeater, utilize the three-dimensional anti-shake cloud platform that unmanned aerial vehicle was equipped with, high-power optics zoom visible light camera and high accuracy infrared thermal imaging camera provide 4k high definition images.
Meanwhile, the unmanned aerial vehicle is provided with a high-definition image transmission system, can patrol the power transmission line in real time, photographs or records each device and channel of the power transmission line, and provides data support for subsequent analysis and processing of actual conditions of the power transmission line.
The mobile unmanned aerial vehicle field operation suit can be flexibly transported to a patrol place by a pickup truck, and the unmanned aerial vehicle is automatically controlled to carry out autonomous and refined patrol operation, and the mobile unmanned aerial vehicle field operation suit comprises an existing unmanned aerial vehicle-ground station system, a vehicle-mounted network system, a vehicle-mounted power supply system, an unmanned aerial vehicle, a battery storage device and an auxiliary module.
In the embodiment, the real-time images are analyzed through the front-end onboard computer, the real-time coordinate data are automatically compared through the neural network algorithm to correct the deviation, so that the high-precision coordinates obtained by the unmanned aerial vehicle are built into the unmanned aerial vehicle high-precision positioning system based on the mixed use of the RTK and the image recognition algorithm, and the aim of automatic planning of the unmanned aerial vehicle high-precision route is achieved according to the preset inspection operation sequences of the standard unmanned aerial vehicle of different tower types under different voltage levels.
The unmanned aerial vehicle comprises a video acquisition unit, and the detection objects are photographed at different waypoints according to the setting in the route.
The edge computing equipment collects information of video acquisition units of different waypoints, simply filters video streams, and then detects each frame of picture based on the neural network.
The airborne computer collects detection results of edge computing equipment, controls the unmanned aerial vehicle and the video acquisition unit according to the detection results, shoots detection objects of different waypoints, records GPS information, time, shooting times, adjustment times, stability and definition of the waypoints, and finally obtains a precise route capable of accurately shooting target detection objects in the same environment.
After the unmanned aerial vehicle takes off, flying around the range of the tower by 3-10 meters, and accurately positioning by using a GPS; the unmanned aerial vehicle sways within the range of 10-50 cm during hovering.
The specific process of simple filtering of the video stream is as follows:
after reaching an waypoint, the video acquisition unit performs large-scale scanning, the edge computing equipment starts a tower identification neural network, firstly identifies the position of the tower closest to the unmanned aerial vehicle, and identifies the type, the direction, the coordinates and the size of the tower from the video stream, wherein the identification speed is 10 frames per second; after the towers are identified, firstly, the towers in each frame are sheared out, so that sundries except the towers are filtered cleanly.
The specific process of detecting each frame of picture based on the neural network is as follows:
and amplifying and photographing each detected insulator in the graph, and switching the neural network to the detected object identification neural network by the edge computing equipment, wherein the edge computing equipment in the embodiment is smart 2.
The neural network carries out detection object identification on the sheared tower pictures, and comprises an insulator, a tower brand, types, orientations, coordinates, sizes and definition of tower top angles and tower bottom supports; at this time, the controller records the unmanned aerial vehicle coordinates, inclination, orientation and camera sitting inclination, orientation as the first pose.
The airborne computer collects detection results of edge computing equipment, and controls the unmanned aerial vehicle and the video collecting unit according to the detection results as follows:
step (1): according to the position of the first insulator in the figure, the controller moves the camera so that the insulator is moved to the very center of the image, wherein the image recognition tracks the insulator at a speed of 10 frames per second;
step (2): gradually amplifying and focusing to ensure that the insulator is larger and larger in the middle, wherein the image recognition speed of 10 frames per second tracks the insulator and calculates whether the insulator is clear or not, and the inclination angle of the camera is continuously controlled to keep the insulator at the center of the image all the time;
step (3): when the insulator is enlarged to 1/4 of the total size of the picture, namely the width and the length are half of the picture, photographing the insulator;
step (4): and (3) restoring the focal length and the inclination angle of the camera to the first pose, and repeating the step (1) for the next insulator.
In the step (1), when tracking the detected objects, a linear matching algorithm is used, a loss matrix is generated by the first frame of detected objects and the second frame of detected objects, and loss values of the two detected objects between the two frames are recorded in the loss matrix;
the greater the likelihood of a match between the test objects, the smaller the loss value; conversely, if the probability of matching between the detected objects is smaller, the loss value is larger; simultaneously generating two false detection objects, wherein all detection objects cannot be matched with each other; the loss value between different detection objects of different frames is determined by the type, coordinates, length-width ratio, definition and color of the different detection objects, and the loss value is generated by different specific weights.
The mobile platform of this embodiment is responsible for storing unmanned aerial vehicle, changing unmanned aerial vehicle battery and ground air communication based on current ordinary pickup truck that patrols and examines. The unmanned aerial vehicle can realize automatic recovery, field storage and energy supply of the unmanned aerial vehicle, and can automatically complete various operations such as inspection, monitoring and the like under the field condition. When the pick-up truck runs under complex road conditions, the unmanned aerial vehicle fixing module can ensure that the unmanned aerial vehicle is stably fixed on field operation complete equipment of the pick-up unmanned aerial vehicle. The unmanned aerial vehicle take-off and landing module can ensure that the unmanned aerial vehicle can safely take off and land under a complex field environment.
The pickup truck for inspection is provided with a vehicle-mounted server system, and the vehicle-mounted server system is a hub for information interaction between a central server and a single vehicle body and is also a brain of field operation equipment of the pickup unmanned aerial vehicle. The system has the functions of receiving task data, triggering tasks, uploading data and the like from the central terminal, and provides an operation page for an operator to perform man-machine interaction. Is an upper computer of other hardware equipment.
Meanwhile, the pickup truck for inspection is provided with a vehicle-mounted ground station system, and the vehicle-mounted ground station system is a module for directly controlling the unmanned aerial vehicle to fly. Before the unmanned aerial vehicle executes the task, the vehicle-mounted server system can distribute the inspection task to the vehicle-mounted ground station system, and the ground station can control the unmanned aerial vehicle to remotely control and send out corresponding control signals to control the unmanned aerial vehicle to fly after processing the task. After the unmanned aerial vehicle finishes the task of patrolling the tower, the vehicle-mounted ground station system can automatically download the data of patrolling and examining to the vehicle-mounted computer system.
The embodiment also sets up the current unmanned aerial vehicle communication repeater that is applicable to high altitude, big difference of elevation area, through the study to aerial signal relay technique, realizes unmanned aerial vehicle and mobile control end's real-time communication, solves unmanned aerial vehicle and is patrolled and examined because the mountain stops the communication interruption problem that leads to when the transmission line in mountain area, establishes a set of unmanned aerial vehicle aerial signal communication repeater that is applicable to high altitude, big difference of elevation area.
The function of the present vehicle-mounted unmanned aerial vehicle operation control system of this embodiment:
(1) The unmanned aerial vehicle has the functions of route management and editing, performs operation tasks and route editing and issuing on known control points, and realizes automatic point A, departure and point B landing of the unmanned aerial vehicle, as shown in fig. 1. After the unmanned aerial vehicle transmits data to the server at the point B, the unmanned aerial vehicle takes off again to execute the next task and automatically lands at the other point A.
(2) The system has the function of real-time transmission of inspection video, and the operation condition is transmitted back to the vehicle-mounted background control system in real time, so that the operation condition of the unmanned aerial vehicle is controlled in real time.
(3) Visualization functions, including but not limited to, flight status, flight path simulation, and the like.
The embodiment is a complete whole-flow inspection solution with complete storage, transportation, autonomous inspection and automatic data return, and the intelligent and automatic inspection is truly realized by combining an advanced software and hardware technology. The method also has the following advantages:
(1) The existing pick-up card can be utilized, modification is not needed, and cost is reduced;
(2) The vehicle body is smaller and the adaptability to complex scenes is strong;
(3) The cost performance is high, and the use cost is low;
(4) The one-key autonomous inspection is supported, manual participation is not needed in the autonomous inspection process, the data is transmitted back to the vehicle-mounted server in real time, and the vehicle-mounted server and the central terminal are synchronous in data in real time, so that the data can be analyzed quickly;
(5) By applying a computer vision technology, positioning is assisted on the basis of high-precision RTK positioning, and automatic inspection and landing are more accurately completed;
(6) Multiple networking modes support access to a client private network system, and ensure the data security of the system;
(7) The pick-up airport does not need vehicle refitting and bulletin, has short production period and simple and convenient annual examination, license plate and other processes.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.

Claims (8)

1. An uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation is characterized in that: the method comprises the following steps:
step (1), data input
Inputting unmanned aerial vehicle and line pole tower information through an unmanned aerial vehicle on-site background management system;
step (2), generating pole tower route data by the master machine
Distributing account information of operators through a background, and downloading corresponding pole tower route data after the operators newly create an operation task; or taking off from a first field mobile platform of the first operation tower by using an unmanned aerial vehicle carrying an onboard computer, flying along a preset rough route, automatically finishing recording of a fine route by the onboard computer during flying, and accurately lowering a second field mobile platform of the second operation tower to generate accurate route data of the tower;
the formation process of the accurate route of the tower is as follows:
the edge computing equipment on the master machine collects information of video acquisition units of different waypoints, simply filters video streams, and then detects each frame of picture based on a neural network;
the method comprises the steps that an airborne computer collects detection results of edge computing equipment, controls an unmanned aerial vehicle and a video acquisition unit according to the detection results, shoots detection objects of different waypoints, records GPS information, time, shooting times, adjustment times, stability and definition of the waypoints, and finally obtains a precise route capable of accurately shooting target detection objects in the same environment;
step (3), automatic fine inspection of the mother machine or the son machine
After the mother machine generates the accurate route, a first team of field operators arrive at a first field mobile platform, a vehicle-mounted unmanned aerial vehicle take-off and landing platform is used for controlling a common unmanned aerial vehicle, or the mother machine is directly used in a complex terrain environment, and automatic and refined inspection of the towers is performed based on the accurate route data; meanwhile, a second team of field operators arrive at a second field mobile platform and send return coordinate data; after the main machine or the sub machine starts to take off and work, the field personnel of the first field mobile platform are transferred to the position of a third working tower; after the second team of field operators fly off the unmanned aerial vehicle, the second team of field operators are transferred to a fourth operation tower position, and the first field mobile platform and the second field mobile platform are alternately used as take-off landing points; until the task is finished.
2. The uninterruptible self-contained main tower inspection method based on multi-machine collaborative operation according to claim 1, which is characterized in that: and (4) landing after the unmanned aerial vehicle finishes operation, carrying out power conversion and data uploading, and landing to a descent point after taking off again and carrying out the next flight operation of the navigation section.
3. The uninterruptible self-mobile tower inspection method based on multi-machine collaborative operation according to claim 2, which is characterized in that: and (5) after finishing the operation task, the operator carries out induction and arrangement on the inspection data and then uploads the inspection data, and the field operation task is finished.
4. The uninterruptible self-contained main tower inspection method based on multi-machine collaborative operation according to claim 1, which is characterized in that: after the unmanned aerial vehicle takes off, flying around the range of the tower by 3-10 meters, and accurately positioning by using a GPS; the unmanned aerial vehicle sways within the range of 10-50 cm during hovering.
5. The uninterruptible self-contained main tower inspection method based on multi-machine collaborative operation according to claim 1, which is characterized in that: the specific process of simple filtering of the video stream is as follows:
after reaching an waypoint, the video acquisition unit performs large-scale scanning, the edge computing equipment starts a tower identification neural network, firstly identifies the position of the tower closest to the unmanned aerial vehicle, and identifies the type, the direction, the coordinates and the size of the tower from the video stream, wherein the identification speed is 10 frames per second; after the towers are identified, firstly, the towers in each frame are sheared out, so that sundries except the towers are filtered cleanly.
6. The uninterruptible self-contained main tower inspection method based on multi-machine collaborative operation according to claim 1, which is characterized in that: the specific process of detecting each frame of picture based on the neural network is as follows:
amplifying and photographing each detected insulator in the graph, and switching the neural network to the object detection recognition neural network by the edge computing equipment; the neural network carries out detection object identification on the sheared tower pictures, and comprises an insulator, a tower brand, types, orientations, coordinates, sizes and definition of tower top angles and tower bottom supports; at this time, the onboard computer records the unmanned aerial vehicle coordinates, inclination angles, orientations, and camera sitting inclination angles, orientations as the first pose.
7. The uninterruptible self-contained tower inspection method based on multi-machine collaborative operation according to claim 6, which is characterized in that: the controller collects detection results of the edge computing equipment, and controls the unmanned aerial vehicle and the video collecting unit according to the detection results as follows:
step (1): based on the position of the first detector in the figure, the controller moves the camera so that the insulator is moved to the very center of the image, wherein image recognition tracks the insulator at a speed of 10 frames per second;
step (2): gradually amplifying and focusing to ensure that the size of the detection object is larger and larger in the middle, wherein the speed of 10 frames per second of image recognition tracks the insulator and calculates whether the insulator is clear or not, and the inclination angle of the camera is continuously controlled to keep the insulator at the center of the image all the time;
step (3): when the detected object is amplified to 1/4 of the total size of the picture, namely the width and the length are half of the picture, photographing the insulator;
step (4): and (3) restoring the focal length and the inclination angle of the camera to the first pose, and repeating the step (1) for the next detected object.
8. The uninterruptible self-contained main tower inspection method based on multi-machine collaborative operation according to claim 1, which is characterized in that: after all the detected objects in the waypoints are scanned, the GPS information, time, photographing times, adjustment times, stability and definition of the waypoints are recorded, the unmanned aerial vehicle flies to the next waypoint, the insulators are photographed again at different angles, and the route recorded after inspection is a precise route capable of accurately photographing the target detection object in the same environment.
CN202010851167.4A 2020-08-21 2020-08-21 Uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation Active CN112162565B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010851167.4A CN112162565B (en) 2020-08-21 2020-08-21 Uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010851167.4A CN112162565B (en) 2020-08-21 2020-08-21 Uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation

Publications (2)

Publication Number Publication Date
CN112162565A CN112162565A (en) 2021-01-01
CN112162565B true CN112162565B (en) 2023-05-30

Family

ID=73859693

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010851167.4A Active CN112162565B (en) 2020-08-21 2020-08-21 Uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation

Country Status (1)

Country Link
CN (1) CN112162565B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112937858A (en) * 2021-01-29 2021-06-11 天津航天中为数据系统科技有限公司 Novel inspection method for vertical take-off and landing fixed wing unmanned aerial vehicle
CN113110580A (en) * 2021-04-19 2021-07-13 山东领亿智能技术有限公司 Multi-machine cooperative inspection system and method for power transmission line
CN113562176A (en) * 2021-08-13 2021-10-29 广东工业大学 Long-range inspection system for remotely-launched unmanned aerial vehicle
CN116301057B (en) * 2023-05-09 2023-09-26 山东智航智能装备有限公司 Unmanned aerial vehicle inspection system and method
CN117388867B (en) * 2023-12-11 2024-04-05 国网辽宁省电力有限公司 Power transmission line inspection method based on high-precision three-dimensional laser point cloud technology

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012110107A (en) * 2010-11-16 2012-06-07 Chugoku Electric Power Co Inc:The Separation confirming device
KR101401524B1 (en) * 2013-03-11 2014-06-03 렉스젠(주) Patrol handset, patrol server and control method for the patrol handset and patrol server
CN108365557A (en) * 2018-02-24 2018-08-03 广东电网有限责任公司肇庆供电局 A kind of method and system of unmanned plane fining inspection transmission line of electricity
CN109272232A (en) * 2018-09-21 2019-01-25 国家电网有限公司 Visualized data management method based on substation's fining inspection business

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103020601B (en) * 2012-12-13 2015-08-05 北京航空航天大学 Hi-line visible detection method and device
CN105098651A (en) * 2014-12-26 2015-11-25 天津航天中为数据系统科技有限公司 Method and system for positioning insulator of power transmission line
CN105023014B (en) * 2015-08-21 2018-11-23 马鞍山市安工大工业技术研究院有限公司 A kind of shaft tower target extraction method in unmanned plane inspection transmission line of electricity image
CN105204522B (en) * 2015-11-16 2017-07-21 国网山东省电力公司莱芜供电公司 A kind of power transmission line unmanned machine relay flight inspection method
CN106295655B (en) * 2016-08-03 2019-07-12 国网山东省电力公司电力科学研究院 A kind of transmission line part extraction method for unmanned plane inspection image
CN106155086B (en) * 2016-08-09 2018-10-30 长安大学 A kind of Road Detection unmanned plane and its automatic cruising method
CN106101658A (en) * 2016-08-13 2016-11-09 哈尔滨理工大学 Shaft tower foreign body and disappearance intelligent video on-line monitoring system
GB2568186A (en) * 2016-09-09 2019-05-08 Walmart Apollo Llc Geographic area monitoring systems and methods utilizing computational sharing across multiple unmanned vehicles
CN108413964A (en) * 2018-03-08 2018-08-17 云南电网有限责任公司电力科学研究院 A kind of unmanned plane polling transmission line path planning method and system
CN109765930B (en) * 2019-01-29 2021-11-30 理光软件研究所(北京)有限公司 Unmanned aerial vehicle vision navigation
CN110134143A (en) * 2019-05-30 2019-08-16 广东电网有限责任公司 A kind of electric inspection process method, system and electronic equipment and storage medium
CN110750106B (en) * 2019-10-16 2023-06-02 深圳市道通智能航空技术股份有限公司 Unmanned aerial vehicle safety route generation method and device, control terminal and unmanned aerial vehicle
CN110908401B (en) * 2019-12-06 2021-03-30 电子科技大学 Unmanned aerial vehicle autonomous inspection method for unknown tower structure
CN111006671B (en) * 2019-12-27 2021-10-15 北京数字绿土科技有限公司 Intelligent route planning method for refined routing inspection of power transmission line
CN111259097B (en) * 2020-01-09 2023-11-24 武汉赛摩博晟信息科技有限公司 Fine waypoint checking method applied to photovoltaic industry unmanned aerial vehicle inspection
CN111311569A (en) * 2020-02-12 2020-06-19 江苏方天电力技术有限公司 Pole tower defect identification method based on unmanned aerial vehicle inspection
CN111401146A (en) * 2020-02-26 2020-07-10 长江大学 Unmanned aerial vehicle power inspection method, device and storage medium
CN111062651A (en) * 2020-03-18 2020-04-24 南京中电科能技术有限公司 Safe power utilization management system and method based on edge calculation and big data analysis
CN111257331B (en) * 2020-03-20 2024-09-06 广东电网有限责任公司 Unmanned aerial vehicle inspection system and inspection method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012110107A (en) * 2010-11-16 2012-06-07 Chugoku Electric Power Co Inc:The Separation confirming device
KR101401524B1 (en) * 2013-03-11 2014-06-03 렉스젠(주) Patrol handset, patrol server and control method for the patrol handset and patrol server
CN108365557A (en) * 2018-02-24 2018-08-03 广东电网有限责任公司肇庆供电局 A kind of method and system of unmanned plane fining inspection transmission line of electricity
CN109272232A (en) * 2018-09-21 2019-01-25 国家电网有限公司 Visualized data management method based on substation's fining inspection business

Also Published As

Publication number Publication date
CN112162565A (en) 2021-01-01

Similar Documents

Publication Publication Date Title
CN112162565B (en) Uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation
US11017228B2 (en) Method and arrangement for condition monitoring of an installation with operating means
CN109765930B (en) Unmanned aerial vehicle vision navigation
CN108109437B (en) Unmanned aerial vehicle autonomous route extraction and generation method based on map features
CN102156481B (en) Intelligent tracking control method and system for unmanned aircraft
CN112326686B (en) Unmanned aerial vehicle intelligent cruising pavement disease detection method, unmanned aerial vehicle and detection system
CN105700544A (en) UAV tour inspection system and implementation method for electrical equipment of photovoltaic power station
CN112327906A (en) Intelligent automatic inspection system based on unmanned aerial vehicle
Niu et al. A UAV-based traffic monitoring system-invited paper
CN111479086A (en) Intelligent real-time command management system for unmanned aerial vehicle
CN114035614A (en) Unmanned aerial vehicle autonomous inspection method and system based on prior information and storage medium
CN110113570A (en) A kind of autonomous cruising inspection system of power transmission line unmanned machine and its working method
CN105120146A (en) Shooting device and shooting method using unmanned aerial vehicle to perform automatic locking of moving object
CN105157708A (en) Unmanned aerial vehicle autonomous navigation system and method based on image processing and radar
CN108258613A (en) Intelligent line patrol photoelectric pod and line patrol realization method
CN110880258A (en) Power line unmanned aerial vehicle intelligent inspection actual operation simulation training method and system
CN113077561A (en) Intelligent inspection system for unmanned aerial vehicle
CN111257331B (en) Unmanned aerial vehicle inspection system and inspection method
CN111006643A (en) Unmanned aerial vehicle remote sensing information monitoring method
CN113568427B (en) Unmanned aerial vehicle autonomous landing mobile platform method and system
CN112947550A (en) Illegal aircraft striking method based on visual servo and robot
CN112327929A (en) Unmanned aerial vehicle aviation flight management system
CN112711267A (en) Unmanned aerial vehicle autonomous inspection method based on RTK high-precision positioning and machine vision fusion
CN114967731A (en) Unmanned aerial vehicle-based automatic field personnel searching method
CN110068827A (en) A kind of method of the autonomous object ranging of unmanned plane

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant